[fix](alarm): make dismissal stick and count the devices

Four defects, three of them the same missing piece of the delivery ledger.

- listSubscriptions scanned nine destinations for ten columns and read a NULL
  subscriber_user_id into a uuid. Every alert with an anonymous subscriber
  answered 500 ("number of field descriptions must equal number of
  destinations, got 10 and 9"), and the client renders a failed read as an
  empty list — so 'Subscribed devices' said 0 while the row existed. The
  listing now uses the same scan as every other subscription read.
- alarmStatus reported the alert's commanded state, not the caller's own. An
  alert stays 'triggered' until the owner disarms or every subscriber acks, so
  a device that had already dismissed the alarm was told active:true on every
  poll and re-raised its takeover. active is now true only while the caller
  still owes the newest trigger; the owner keeps seeing their own alert.
- ackAlarm required an eventId, which the native takeover launch does not
  have. A dismissal that cannot name its event now clears the subscription's
  whole outstanding set (AckAllDeliveries / AckAllForSubscriber), so the debt
  cannot survive because the client could not echo a uuid.
- The device ledger probe (gated on DATABASE_URL, like the lifecycle probe)
  pins the per-subscriber debt, the ack-all semantics and the cascade that
  takes a device token with the destroyed alert.

Verified against the dev database and through Maestro: 2 subscriptions listed,
device A acked -> its status turns active:false while device B still gets the
409 check-in, ack-all without eventId clears the debt and drains the alert.

src/actions/ack.go

@@ -63,15 +63,19 @@ func AckAlarm(w http.ResponseWriter, r *http.Request, payload any) {
 		validationError(w, "%v", err)
 		return
 	}
-	eventRaw := fieldOrQuery(r, payload, "eventId")
-	if eventRaw == "" {
-		validationError(w, "eventId is required")
-		return
-	}
-	eventID, err := uuid.Parse(eventRaw)
-	if err != nil {
-		validationError(w, "eventId is not a valid uuid")
-		return
+	// eventId is optional on purpose. The native takeover launch carries only the
+	// alert, so a dismissal from that path has no event to name; "I have heard
+	// this device's alarm" is then answered by clearing the caller's whole
+	// outstanding set (see db.AckAllDeliveries). A stale debt that nobody can
+	// name must not replay forever because the client could not echo a uuid.
+	var eventID uuid.UUID
+	if eventRaw := fieldOrQuery(r, payload, "eventId"); eventRaw != "" {
+		parsed, err := uuid.Parse(eventRaw)
+		if err != nil {
+			validationError(w, "eventId is not a valid uuid")
+			return
+		}
+		eventID = parsed
 	}
 
 	alert, err := db.GetAlert(r.Context(), alertID)
@@ -96,12 +100,21 @@ func AckAlarm(w http.ResponseWriter, r *http.Request, payload any) {
 		}
 	}
 
-	resp := ackAlarmResponse{AlertID: alertID.String(), EventID: eventID.String()}
+	resp := ackAlarmResponse{AlertID: alertID.String()}
+	if eventID != uuid.Nil {
+		resp.EventID = eventID.String()
+	}
 
 	// A device token lives on the subscription, so the ledger row is addressed
 	// directly: no user id, no device-id echo, nothing to spoof.
 	if c.IsDevice {
-		cleared, err := db.AckDelivery(r.Context(), alertID, c.Sub.ID, eventID)
+		var cleared int64
+		var err error
+		if eventID == uuid.Nil {
+			cleared, err = db.AckAllDeliveries(r.Context(), alertID, c.Sub.ID)
+		} else {
+			cleared, err = db.AckDelivery(r.Context(), alertID, c.Sub.ID, eventID)
+		}
 		if err != nil {
 			dbError(w, action, err)
 			return
@@ -119,7 +132,8 @@ func AckAlarm(w http.ResponseWriter, r *http.Request, payload any) {
 			}
 			resp.Destroyed = destroyed
 		}
-		Debug(action, "POST", "alert=%s event=%s acked=%d destroyed=%t (device)", alertID, eventID, resp.Acked, resp.Destroyed)
+		Debug(action, "POST", "alert=%s event=%s all=%t acked=%d destroyed=%t (device)",
+			alertID, resp.EventID, eventID == uuid.Nil, resp.Acked, resp.Destroyed)
 		writeJSON(w, http.StatusOK, resp)
 		return
 	}
@@ -132,7 +146,13 @@ func AckAlarm(w http.ResponseWriter, r *http.Request, payload any) {
 			validationError(w, "%v", err)
 			return
 		}
-		cleared, err := db.AckAlarmDelivery(r.Context(), alertID, c.UserID, deviceid.Hash(raw), eventID)
+		deviceHash := deviceid.Hash(raw)
+		var cleared int64
+		if eventID == uuid.Nil {
+			cleared, err = db.AckAllForSubscriber(r.Context(), alertID, c.UserID, deviceHash)
+		} else {
+			cleared, err = db.AckAlarmDelivery(r.Context(), alertID, c.UserID, deviceHash, eventID)
+		}
 		if err != nil {
 			dbError(w, action, err)
 			return
@@ -152,7 +172,8 @@ func AckAlarm(w http.ResponseWriter, r *http.Request, payload any) {
 		}
 	}
 
-	Debug(action, "POST", "alert=%s event=%s acked=%d destroyed=%t", alertID, eventID, resp.Acked, resp.Destroyed)
+	Debug(action, "POST", "alert=%s event=%s all=%t acked=%d destroyed=%t",
+		alertID, resp.EventID, eventID == uuid.Nil, resp.Acked, resp.Destroyed)
 	writeJSON(w, http.StatusOK, resp)
 }
 

src/actions/events.go

@@ -225,6 +225,12 @@ func AlarmStatus(w http.ResponseWriter, r *http.Request, payload any) {
 	// 409 lost in transit must not forfeit the alarm: the next check-in has to
 	// find the same row. A trigger that has since been disarmed is not news, so
 	// that case falls through to the normal body (active:false).
+	deviceHash := ""
+	if !c.IsDevice {
+		if raw := strings.TrimSpace(r.URL.Query().Get("deviceId")); raw != "" {
+			deviceHash = deviceid.Hash(raw)
+		}
+	}
 	var pending *db.PendingDelivery
 	if c.IsDevice {
 		// The device token already identifies the subscription, so its whole
@@ -238,10 +244,6 @@ func AlarmStatus(w http.ResponseWriter, r *http.Request, payload any) {
 			pending = &rows[0]
 		}
 	} else {
-		deviceHash := ""
-		if raw := strings.TrimSpace(r.URL.Query().Get("deviceId")); raw != "" {
-			deviceHash = deviceid.Hash(raw)
-		}
 		var err error
 		pending, err = db.PendingTrigger(r.Context(), alertID, c.UserID, deviceHash)
 		if err != nil && !errors.Is(err, db.ErrNotFound) {
@@ -261,6 +263,27 @@ func AlarmStatus(w http.ResponseWriter, r *http.Request, payload any) {
 		// not live even if the stored status says "triggered".
 		active = false
 	}
+	// "Active" is a statement about THIS caller, not about the alert's commanded
+	// status. The alert stays triggered until the owner disarms it or every
+	// subscriber acknowledges, so answering a device that already dismissed the
+	// alarm with active:true makes a correct client re-raise the takeover on
+	// every poll — the alarm that will not stay dismissed. A subscriber is
+	// active only while it still owes the newest trigger; the owner (who has no
+	// delivery row) keeps seeing their own alert as live.
+	callerIsOwner := !c.IsDevice && res.Alert.AdminUserID == c.UserID
+	if active && !callerIsOwner {
+		var owed bool
+		if c.IsDevice {
+			owed, err = db.HasPendingDelivery(r.Context(), alertID, c.Sub.ID)
+		} else {
+			owed, err = db.HasPendingDeliveryForUser(r.Context(), alertID, c.UserID, deviceHash)
+		}
+		if err != nil {
+			dbError(w, action, err)
+			return
+		}
+		active = owed
+	}
 
 	view := statusView{
 		Active:     active,

src/db/deliveries.go

@@ -166,3 +166,82 @@ func AckAlarmDelivery(ctx context.Context, alertID, userID uuid.UUID, deviceID s
 	}
 	return tag.RowsAffected(), nil
 }
+
+// HasPendingDelivery reports whether a subscription still owes an alarm — the
+// question `alarmStatus` has to ask before it calls an alert "active".
+//
+// An alert stays commanded "triggered" until the owner disarms it or every
+// subscriber acknowledges, so the commanded status alone is not the caller's
+// answer: a device that already dismissed the alarm must be told it owes
+// nothing, or it re-raises the same takeover forever.
+func HasPendingDelivery(ctx context.Context, alertID, subscriptionID uuid.UUID) (bool, error) {
+	var owed bool
+	err := Pool().QueryRow(ctx,
+		`SELECT EXISTS (
+		    SELECT 1 FROM alarm.alarm_deliveries
+		     WHERE alert_id = $1 AND subscription_id = $2 AND acked_at IS NULL)`,
+		alertID, subscriptionID).Scan(&owed)
+	if err != nil {
+		return false, err
+	}
+	return owed, nil
+}
+
+// HasPendingDeliveryForUser is the account-path equivalent: the caller's debt is
+// addressed by (alert, user, device) exactly like the socket and the ack, with
+// an empty device hash meaning "any of this user's subscriptions on the alert".
+func HasPendingDeliveryForUser(ctx context.Context, alertID, userID uuid.UUID, deviceHash string) (bool, error) {
+	var owed bool
+	err := Pool().QueryRow(ctx,
+		`SELECT EXISTS (
+		    SELECT 1
+		      FROM alarm.alarm_deliveries d
+		      JOIN alarm.subscriptions s ON s.id = d.subscription_id
+		     WHERE d.alert_id = $1
+		       AND d.acked_at IS NULL
+		       AND s.subscriber_user_id = $2
+		       AND ($3 = '' OR s.device_id = $3))`,
+		alertID, userID, deviceHash).Scan(&owed)
+	if err != nil {
+		return false, err
+	}
+	return owed, nil
+}
+
+// AckAllDeliveries clears every alarm this subscription still owes, and reports
+// how many rows it retired. It is the dismissal that does not know an event id —
+// a native takeover launch carries only the alert, and re-deriving "which
+// trigger was I ringing for" from the phone is guesswork. Acknowledging means
+// "this device has heard the alarm", so clearing the whole outstanding set is
+// the honest reading and the one that cannot leave a stale debt replaying.
+func AckAllDeliveries(ctx context.Context, alertID, subscriptionID uuid.UUID) (int64, error) {
+	tag, err := Pool().Exec(ctx,
+		`UPDATE alarm.alarm_deliveries
+		    SET acked_at = now()
+		  WHERE alert_id = $1 AND subscription_id = $2 AND acked_at IS NULL`,
+		alertID, subscriptionID)
+	if err != nil {
+		return 0, err
+	}
+	return tag.RowsAffected(), nil
+}
+
+// AckAllForSubscriber is AckAllDeliveries for the account path, addressed by
+// (alert, user, device) so a caller can only ever clear its own debt.
+func AckAllForSubscriber(ctx context.Context, alertID, userID uuid.UUID, deviceHash string) (int64, error) {
+	tag, err := Pool().Exec(ctx,
+		`UPDATE alarm.alarm_deliveries d
+		    SET acked_at = now()
+		  WHERE d.alert_id = $1
+		    AND d.acked_at IS NULL
+		    AND d.subscription_id IN (
+		        SELECT s.id FROM alarm.subscriptions s
+		        WHERE s.alert_id = $1
+		          AND s.subscriber_user_id = $2
+		          AND ($3 = '' OR s.device_id = $3))`,
+		alertID, userID, deviceHash)
+	if err != nil {
+		return 0, err
+	}
+	return tag.RowsAffected(), nil
+}

src/db/device_ledger_db_test.go

@@ -0,0 +1,133 @@
+// Copyright (C) 2026 Dcntrlized
+//
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published
+// by the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+//
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+package db
+
+// The device-ledger probe: what an anonymous subscriber's dismissal does to the
+// delivery ledger. Skipped unless DATABASE_URL points at a migrated database
+// (same gate as TestLedgerProbe):
+//
+//	DATABASE_URL='postgres://postgres:…@127.0.0.1:55432/dcntrlized?sslmode=disable' \
+//	  go test -run TestDeviceLedgerProbe -count=1 -v ./db/
+//
+// It proves the three queries `alarmStatus` and `ackAlarm` now depend on:
+//   - a device subscription with no user id still owes (and clears) alarms;
+//   - an "ack all" dismissal retires the whole outstanding set, which is how a
+//     native takeover launch (no event id) stops a replay loop;
+//   - "does this caller owe the alarm?" answers per subscriber, so one device
+//     dismissing does not silence another device's owed alarm.
+
+import (
+	"context"
+	"os"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/google/uuid"
+)
+
+func TestDeviceLedgerProbe(t *testing.T) {
+	dsn := os.Getenv("DATABASE_URL")
+	if dsn == "" {
+		t.Skip("DATABASE_URL not set; device ledger probe needs a migrated database")
+	}
+	ctx := context.Background()
+	NewDB()
+	t.Cleanup(Close)
+
+	admin := uuid.New()
+	account := uuid.New()
+	msg := "probe"
+	a, err := CreateAlert(ctx, &Alert{
+		AdminUserID:    admin,
+		Name:           "probe device ledger",
+		Message:        &msg,
+		AdminTokenHash: []byte("probe"),
+		SubscribeToken: "probe-" + uuid.NewString(),
+		ExpiresAt:      time.Now().UTC().Add(time.Hour),
+	})
+	if err != nil {
+		t.Fatalf("CreateAlert: %v", err)
+	}
+	t.Cleanup(func() {
+		_, _ = Pool().Exec(context.Background(), `DELETE FROM alarm.alerts WHERE id = $1`, a.ID)
+	})
+
+	tokenHash := strings.Repeat("c", 64)
+	device, err := CreateSubscription(ctx, &Subscription{
+		AlertID:         a.ID,
+		DeviceID:        "sha256:" + strings.Repeat("d", 64),
+		DeviceTokenHash: &tokenHash,
+	})
+	if err != nil {
+		t.Fatalf("CreateSubscription (device): %v", err)
+	}
+	if _, err := CreateSubscription(ctx, &Subscription{
+		AlertID: a.ID, SubscriberUserID: account, DeviceID: "sha256:" + strings.Repeat("e", 64),
+	}); err != nil {
+		t.Fatalf("CreateSubscription (account): %v", err)
+	}
+
+	_, event, err := TriggerAlert(ctx, a.ID, admin, nil)
+	if err != nil {
+		t.Fatalf("TriggerAlert: %v", err)
+	}
+	if ok, err := HasPendingDelivery(ctx, a.ID, device.ID); err != nil || !ok {
+		t.Fatalf("device owes after trigger: %v %v", ok, err)
+	}
+	if ok, err := HasPendingDeliveryForUser(ctx, a.ID, account, ""); err != nil || !ok {
+		t.Fatalf("account owes after trigger: %v %v", ok, err)
+	}
+
+	// The device dismissal that names no event clears its whole set; a repeat
+	// (or a named ack afterwards) is an idempotent no-op.
+	cleared, err := AckAllDeliveries(ctx, a.ID, device.ID)
+	if err != nil || cleared != 1 {
+		t.Fatalf("AckAllDeliveries = %d, %v; want 1", cleared, err)
+	}
+	if again, err := AckDelivery(ctx, a.ID, device.ID, event.ID); err != nil || again != 0 {
+		t.Fatalf("AckDelivery after ack-all = %d, %v; want 0", again, err)
+	}
+	if ok, err := HasPendingDelivery(ctx, a.ID, device.ID); err != nil || ok {
+		t.Fatalf("device still owes after ack-all: %v %v", ok, err)
+	}
+	replay, err := PendingReplay(ctx, a.ID, device.ID)
+	if err != nil || len(replay) != 0 {
+		t.Fatalf("device replay after ack-all = %d rows, %v; want 0", len(replay), err)
+	}
+
+	// The other subscriber's debt is untouched: acking is per subscription.
+	if destroyed, err := CompleteAlertDeliveries(ctx, a.ID); err != nil || destroyed {
+		t.Fatalf("alert destroyed while another subscriber still owes: %v %v", destroyed, err)
+	}
+	if ok, err := HasPendingDeliveryForUser(ctx, a.ID, account, ""); err != nil || !ok {
+		t.Fatalf("account debt lost when the device acked: %v %v", ok, err)
+	}
+	if got, err := AckAllForSubscriber(ctx, a.ID, account, ""); err != nil || got != 1 {
+		t.Fatalf("AckAllForSubscriber = %d, %v; want 1", got, err)
+	}
+	if destroyed, err := CompleteAlertDeliveries(ctx, a.ID); err != nil || !destroyed {
+		t.Fatalf("last ack did not destroy the alert: %v %v", destroyed, err)
+	}
+
+	// The alert, its subscriptions and the device's token row are all gone.
+	if ok, err := HasPendingDelivery(ctx, a.ID, device.ID); err != nil || ok {
+		t.Fatalf("device owes on a destroyed alert: %v %v", ok, err)
+	}
+	if _, err := GetSubscriptionByToken(context.Background(), tokenHash); err == nil {
+		t.Fatalf("device token still resolves after the alert was destroyed")
+	}
+}

src/db/subscriptions.go

@@ -169,12 +169,15 @@ func ListSubscriptions(ctx context.Context, alertID uuid.UUID) ([]Subscription,
 
 	out := make([]Subscription, 0, 4)
 	for rows.Next() {
-		var s Subscription
-		if err := rows.Scan(&s.ID, &s.AlertID, &s.SubscriberUserID, &s.DeviceID, &s.DeviceLabel,
-			&s.Platform, &s.Enabled, &s.LastSeenAt, &s.Created); err != nil {
+		// Same scan as every other read: subscriber_user_id is NULL for a device
+		// subscription (rev 10) and device_token_hash is part of the column set,
+		// so a hand-written destination list here drifts and breaks the listing
+		// for exactly the rows anonymous access creates.
+		s, err := scanSubscription(rows)
+		if err != nil {
 			return nil, err
 		}
-		out = append(out, s)
+		out = append(out, *s)
 	}
 	return out, rows.Err()
 }